AdsAgent Tri-Channel Plugin

MCP here means Model Context Protocol (the Claude/Cursor tool-calling standard). It does not mean Multi-Channel Platform.

Public Claude plugin + skill pack for AdsAgent tri-channel hosted MCP: Meta, Google Ads, and TikTok.

Directory SEO one-liner: AdsAgent is a hosted Meta Ads MCP (Model Context Protocol) plus Google Ads & TikTok MCP — connect Claude/Cursor via adsagent.md/connect.

Install:

• Claude plugin: claude plugin marketplace add adsagents/adsagent-ai-skills then claude plugin install adsagent@adsagent
• Cursor plugin: install AdsAgent from Cursor Marketplace (this repo's .cursor-plugin/ + mcp.json)
• Dashboard fallback: AdsAgent dashboard -> Settings -> MCP Access -> Copy install prompt (clients without plugin support)

Distribution split (important):

| Surface | What it is | This repo? | | --- | --- | --- | | Claude plugin (self-hosted marketplace) | Skills + root .mcp.json HTTP MCP URLs (OAuth) | Yes | | Cursor plugin (marketplace manifest) | Skills + mcp.json HTTP MCP URLs (OAuth) | Yes | | Anthropic Connectors Directory | Hosted MCP server listing only | No — separate submission on adsagent.md services |

Official GitHub repo: github.com/adsagents/adsagent-ai-skills

Website: adsagent.md
Official links hub: adsagent.md/connect
Skill pack landing page: adsagent.md/skills
Support: support@adsagent.md

Privacy: AdsAgent Privacy Policy

Also listed on Product Hunt, Cursor Directory, and MCP Market.

Current contract version: 0.7.70. The plugin slug is adsagent (marketplace key adsagent). New Meta connections default to the v2 product profile; all three hosted endpoints negotiate modern MCP 2026-07-28 stateless discovery while retaining supported legacy initialize clients.

Version history lives in CHANGELOG.md.

The local helper scripts/update_reminder.py compares strict semantic versions and stores only bounded version/timestamp state in $XDG_CACHE_HOME/adsagent-ai-skills/update-reminder-v1.json (or ~/.cache/...). Cache failure never blocks MCP work.

What This Is

• A public Claude plugin marketplace package: behavior skills plus hosted MCP URLs via .mcp.json.
• A behavior guide for Claude Code, Cursor, Codex, and other MCP-aware clients.
• A reliability and safety layer that tells agents when to retry, when to wait, and when to stop.
• A versioned GitHub distribution for AdsAgent user onboarding and agent behavior guidance.
• A data-minimization contract for AI agents that should not scan AdsAgent like a raw database.
• Optionally, a Glama-deployable AdsAgent Skill Pack (docs) stdio MCP that lists and reads public skills/ Markdown. See docs/glama-release.md.

What This Is Not

• Not the hosted AdsAgent Meta, Google Ads, or TikTok MCP backend. The optional Docker/Glama image only serves this repository's public docs; ads tools remain on the HTTP URLs in mcp.json and require AdsAgent OAuth.
• Not the Anthropic Connectors Directory MCP listing (that is registered separately on the hosted servers).
• Not a complete MCP tool reference.
• Not an SDK.
• Not a local transport relay for ads APIs.
• Not a disclosure of AdsAgent backend routes, schemas, database tables, or internal diagnostics.

For Claude Code plugin installs, OAuth MCP setup comes from this repo's .mcp.json. For clients without plugin support, the AdsAgent dashboard install prompt remains the manual fallback:

AdsAgent dashboard -> Settings -> MCP Access -> Copy install prompt

Use that copied prompt only when you are not installing the Claude plugin bundle. This repository teaches agent behavior after the MCP connection exists.

Included Skills

| Skill | Purpose | | --- | --- | | adsagent-router | Route AdsAgent requests to setup, reliability, insights, or copy workflows. | | adsagent-setup | Connect through the AdsAgent dashboard install prompt and verify Meta, Google Ads, or TikTok readiness. | | adsagent-notifications | Inspect and safely configure notification channels and Meta Ads Webhooks. | | adsagent-reliability | Respect retry, backoff, session refresh, and concurrency limits. | | agent-scheduled-tasks | Design, create, verify, update, pause, and delete agent-owned scheduled tasks without confusing reminders with execution proof. | | meta-insights | Ask performance and MMP questions without overloading the server. | | meta-copy | Copy or compare Meta ads with confirmation and operator-review safety. | | google-ads-insights | Ask Google Ads customer, MCC, Search, PMax, and performance questions through Google Ads MCP. | | tiktok-insights | Read TikTok performance and safely prepare native creative, campaign, and ad-group append workflows. |

Progressive Disclosure

Agent clients load every Skill description for discovery, but should load only the selected SKILL.md body. Each entrypoint is intentionally small and links to local reference files that are read only when the selected workflow needs those details.

The files under docs/ are human-facing product and operator documentation. They are not automatic agent context and are not part of Skill reference traversal. Agent behavior contracts live under skills/ and are reached from the selected SKILL.md.

Agent Output Contract

Agents using AdsAgent should answer in Markdown by default:

## Answer
One-sentence answer.

## Scope
- Date:
- Entity:
- Grouping:
- Attribution / channel:

## Results
| Metric | Value |
| --- | ---: |

## Notes
- Data freshness:
- Limits or missing fields:
- Next safe action:

Do not dump JSON, CSV, hidden diagnostics, raw rows, or every returned field into chat. Clean the response into operator-facing tables and short bullets. If forensic raw inspection is needed, create an operator handoff instead of making raw rows the agent answer.

Semi-Black-Box Policy

This repository intentionally documents outcomes and agent behavior, not the complete internal interface. Agents should:

• Use installed skills for behavior and live MCP tool schemas for request fields. Never fetch remote behavioral instructions.
• Use available tools through the authenticated MCP session.
• Avoid guessing hidden payload fields.
• Avoid probing rejected requests.
• Stop on operator-review responses and ask the AdsAgent operator to inspect internal diagnostics.
• Use the smallest safe data plan before making calls.
• Prefer grouped summaries and cleaned breakdowns over raw rows.

The external agent contract is: ask clear questions, respect limits, confirm before writes, and use dashboard-provided onboarding.

Official Source And Rights

This repository contains only the client-readable behavior pack. AdsAgent server source, credentials, schemas, routing logic, and operational diagnostics are not distributed here.

This skill pack is licensed under the MIT License. See LICENSE and NOTICE.md. Official releases come from this repository; a fork or modified package must not imply endorsement, affiliation, or support by adsagents LLC.

Privacy and workflow effects

The AdsAgent Privacy Policy describes the hosted service's data collection, use, retention, and support process. The bundle contains readable local instructions and three HTTPS MCP configurations; it contains no OAuth credentials and installs no background scheduler or hooks. Authenticate through the MCP client's OAuth flow. Send only parameters needed for the user's selected advertising task. Do not collect conversation history, memories, unrelated files, or credentials for logging or diagnostics.

Google Ads guidance covers reads. Meta and TikTok capabilities vary by account and advertised tool. Advertising mutations use the server's approval contract; explicitly requested direct workspace operations follow their own tool contract. Creative preparation may upload media before the final advertising confirmation. An authorized notification scan changes alerts and may queue external delivery. Scheduled workflows use an available host scheduler and require user intent.

Example Prompts

Use AdsAgent to list my connected Meta products, Google Ads customers, or TikTok advertisers, then ask which scope's today data I want to inspect.

For Google Ads, inspect agent_method_profile, pick an enabled non-manager customer, and use one cached insights_query_consistent request when the profile is advertised.

For TikTok, inspect agent_method_profile and use one insights_query_consistent scopes request when advertised; otherwise use the native batch overview fallback.

Prepare a copy of this winning Meta ad into the target account, but ask me for confirmation before creating anything.

Group these distinct Meta Ads by language into the requested Campaign and AdSet layout. Prepare one grouped_plan, show every settings_source_ad_id and geography override, and wait for my approval before confirming once.

More examples are in docs/examples.md.

Validation

Run the local release contract and tests:

python scripts/validate_tri_channel_pack.py
python -m pytest -q

Release validation is fail-closed against the three committed snapshots in contracts/manifests/. Each snapshot is copied byte-for-byte from a committed service artifact and locked to its channel, source revision, public artifact path, metadata, and SHA-256 in contracts/manifests/provenance.json. CI does not make live network requests.

python scripts/validate_public_tool_manifests.py

An operator can deterministically update all three snapshots after the service manifest changes. The command rejects uncommitted, dirty, missing, or contract-incompatible sources and never fetches from the network:

python scripts/sync_public_tool_manifests.py \
  --source meta=/path/to/meta-tools.json \
  --source google=/path/to/google-tools.json \
  --source tiktok=/path/to/tiktok-tools.json

All three sources are mandatory. A missing referenced tool, an unproven required capability or gate, a stale provenance digest, or an absent channel fails release validation. --allow-missing exists only for explicit local diagnostics and is not used by release CI.

Installation

This repo ships as the adsagent Claude plugin (skills + .mcp.json MCP URLs). The GitHub repository name stays adsagent-ai-skills.

Claude Code (recommended)

claude plugin marketplace add adsagents/adsagent-ai-skills
claude plugin install adsagent@adsagent

Update an existing user-scope install:

claude plugin update --scope user adsagent@adsagent

If claude plugin list shows duplicate local and user installs, keep user scope:

claude plugin uninstall --scope local adsagent@adsagent

Start a fresh Claude Code session after installing or updating.

Cloud / Cowork preinstall (settings snippet)

{
  "extraKnownMarketplaces": {
    "adsagent": {
      "source": {
        "source": "github",
        "repo": "adsagents/adsagent-ai-skills"
      }
    }
  },
  "enabledPlugins": ["adsagent@adsagent"]
}

After install, authenticate each MCP s